# Stokes-Informed Diffusion for Robust Linear Polarization Estimation

arXiv: https://arxiv.org/abs/2607.21239 · HTML: https://mlsanity.com/paper/2607.21239/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 45 references that are in the map.
- First posted on arXiv 23 Jul 2026.

## Builds on (most cited first, 16 of 16)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [Polarized Reflection Removal with Perfect Alignment in the Wild](https://mlsanity.com/paper/2003.12789/) (2020)
- [Shape from Polarization for Complex Scenes in the Wild](https://mlsanity.com/paper/2112.11377/) (2021)
- [NeISF: Neural Incident Stokes Field for Geometry and Material Estimation](https://mlsanity.com/paper/2311.13187/) (2023)
- [Polarization-driven Semantic Segmentation via Efficient Attention-bridged Fusion](https://mlsanity.com/paper/2011.13313/) (2020)
- [PolarFree: Polarization-based Reflection-free Imaging](https://mlsanity.com/paper/2503.18055/) (2025)
- [PIDSR: Complementary Polarized Image Demosaicing and Super-Resolution](https://mlsanity.com/paper/2504.07758/) (2025)
- [Simultaneous Acquisition of High Quality RGB Image and Polarization Information using a Sparse Polarization Sensor](https://mlsanity.com/paper/2209.13106/) (2022)
- [Spectral and Polarization Vision: Spectro-polarimetric Real-world Dataset](https://mlsanity.com/paper/2311.17396/) (2023)
- [RGB-to-Polarization Estimation: A New Task and Benchmark Study](https://mlsanity.com/paper/2505.13050/) (2025)
- [PolarAnything: Diffusion-based Polarimetric Image Synthesis](https://mlsanity.com/paper/2507.17268/) (2025)
- [Polarization Denoising and Demosaicking: Dataset and Baseline Method](https://mlsanity.com/paper/2509.10098/) (2025)
- [Polarization Uncertainty-Guided Diffusion Model for Color Polarization Image Demosaicking](https://mlsanity.com/paper/2602.23847/) (2026)

## Built on by (most cited first, 2 of 2)

- [DensePol: Dense-Angle Polarization Dataset for Learning-Based Polarimetric Vision](https://mlsanity.com/paper/2609.09359/) (2026)
- [Learning Polarization Image Restoration with General Restoration Priors](https://mlsanity.com/paper/2609.30728/) (2026)

## Abstract (arXiv)

Polarization cues benefit applications such as material detection and de-reflection, yet acquiring them typically requires dedicated hardware. This motivates us to estimate the linear polarization from a single RGB image. However, the task is inherently ill-posed, with the Angle of Polarization (AoP) becoming particularly unstable in weak polarization regions, where the polarimetric signal is overwhelmed by noise, leading to erratic angle estimates. To address these limitations, we propose GenPolar, a Stokes-informed diffusion framework grounded in the Mueller formalism from an intensity observation. Specifically, GenPolar predicts channel-wise linear Stokes components (S1,S2) from intensity S0, from which degree of linear polarization (DoLP) and AoP are analytically derived; AoP is further supervised with an observability-aware loss. In addition, to enable efficient and high-fidelity inference, we adopt a two-stage training strategy. Firstly, a multi-step conditional diffusion model is trained with a physics-based loss. Subsequently, we distill it into a one-step generator, which further supports stable Low-Rank Adaptation (LoRA) of the VAE encoder to mitigate domain-specific autoencoding bias. Extensive experiments across rotating-polarizer, division-of-focal-plane, and hybrid datasets demonstrate that GenPolar achieves state-of-the-art performance in both DoLP fidelity and AoP stability. Crucially, these improvements translate to significant and consistent gains in downstream applications, including material detection and de-reflection.